CellNet: A Lightweight Model towards Accurate LOC-Based High-Speed Cell Detection

doi:10.3390/electronics11091407

CORC > 自动化研究所 > 中国科学院自动化研究所 > 精密感知与控制研究中心 > 精密感知与控制

	CellNet: A Lightweight Model towards Accurate LOC-Based High-Speed Cell Detection
	Long, Xianlei 2,3; Ishii, Idaku 1; Gu, Qingyi 3
刊名	ELECTRONICS
	2022-05-01
卷号	11 期号:9 页码:20
关键词	cell detection high-speed vision convolutional neural network (CNN) efficient convolutional block medical image analysis
DOI	10.3390/electronics11091407
通讯作者	Gu, Qingyi(qingyi.gu@ia.ac.cn)
英文摘要	Label-free cell separation and sorting in a microfluidic system, an essential technique for modern cancer diagnosis, resulted in high-throughput single-cell analysis becoming a reality. However, designing an efficient cell detection model is challenging. Traditional cell detection methods are subject to occlusion boundaries and weak textures, resulting in poor performance. Modern detection models based on convolutional neural networks (CNNs) have achieved promising results at the cost of a large number of both parameters and floating point operations (FLOPs). In this work, we present a lightweight, yet powerful cell detection model named CellNet, which includes two efficient modules, CellConv blocks and the h-swish nonlinearity function. CellConv is proposed as an effective feature extractor as a substitute to computationally expensive convolutional layers, whereas the h-swish function is introduced to increase the nonlinearity of the compact model. To boost the prediction and localization ability of the detection model, we re-designed the model's multi-task loss function. In comparison with other efficient object detection methods, our approach achieved state-of-the-art 98.70% mean average precision (mAP) on our custom sea urchin embryos dataset with only 0.08 M parameters and 0.10 B FLOPs, reducing the size of the model by 39.5 x and the computational cost by 4.6 x. We deployed CellNet on different platforms to verify its efficiency. The inference speed on a graphics processing unit (GPU) was 500.0 fps compared with 87.7 fps on a CPU. Additionally, CellNet is 769.5-times smaller and 420 fps faster than YOLOv3. Extensive experimental results demonstrate that CellNet can achieve an excellent efficiency/accuracy trade-off on resource-constrained platforms.
资助项目	Scientific Instrument Developing Project of the Chinese Academy of Sciences[YJKYYQ20200045]
WOS关键词	CLASSIFICATION ; AUTOENCODER ; EFFICIENT ; NUCLEI
WOS研究方向	Computer Science ; Engineering ; Physics
语种	英语
出版者	MDPI
WOS记录号	WOS:000794685000001
资助机构	Scientific Instrument Developing Project of the Chinese Academy of Sciences
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/49380]
专题	精密感知与控制研究中心_精密感知与控制
通讯作者	Gu, Qingyi
作者单位	1.Hiroshima Univ, Grad Sch Adv Sci & Engn, Smart Robot Lab, Hiroshima 7398527, Japan 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Long, Xianlei,Ishii, Idaku,Gu, Qingyi. CellNet: A Lightweight Model towards Accurate LOC-Based High-Speed Cell Detection[J]. ELECTRONICS,2022,11(9):20.
APA	Long, Xianlei,Ishii, Idaku,&Gu, Qingyi.(2022).CellNet: A Lightweight Model towards Accurate LOC-Based High-Speed Cell Detection.ELECTRONICS,11(9),20.
MLA	Long, Xianlei,et al."CellNet: A Lightweight Model towards Accurate LOC-Based High-Speed Cell Detection".ELECTRONICS 11.9(2022):20.